Related papers: Bit-Identical Medical Deep Learning via Structured…

This paper concludes a series of studies on the polyharmonic cascade, a deep machine learning architecture theoretically derived from indifference principles and the theory of random functions. A universal initialization procedure is…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

Clinical trials require strict adherence to medication protocols, yet dosing errors remain a persistent challenge affecting patient safety and trial integrity. We present an automated system for detecting dosing errors in unstructured…

In clinical practice, medical segmentation datasets are often limited and heterogeneous, with variations in modalities, protocols, and anatomical targets across institutions. Existing deep learning models struggle to jointly learn from such…

Standard neural network training uses constant momentum (typically 0.9), a convention dating to 1964 with limited theoretical justification for its optimality. We derive a time-varying momentum schedule from the critically damped harmonic…

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

The increasing compute demands of AI systems have led to the emergence of services that train models on behalf of clients lacking necessary resources. However, ensuring correctness of training and guarding against potential training-time…

Deep learning models for medical data are typically trained using task specific objectives that encourage representations to collapse onto a small number of discriminative directions. While effective for individual prediction problems, this…

Although deep learning has advanced automated electrocardiogram (ECG) diagnosis, prevalent supervised methods typically treat recordings as undifferentiated one-dimensional (1D) signals or two-dimensional (2D) images. This formulation…

In this paper, an unsupervised steganalysis method that combines artificial training setsand supervised classification is proposed. We provide a formal framework for unsupervisedclassification of stego and cover images in the typical…

When it comes to the classification of brain signals in real-life applications, the training and the prediction data are often described by different distributions. Furthermore, diverse data sets, e.g., recorded from various subjects or…

Despite the recent success of stochastic gradient descent in deep learning, it is often difficult to train a deep neural network with an inappropriate choice of its initial parameters. Even if training is successful, it has been known that…

Electrocardiography is a very common, non-invasive diagnostic procedure and its interpretation is increasingly supported by automatic interpretation algorithms. The progress in the field of automatic ECG interpretation has up to now been…

Peer-to-peer deep learning algorithms are enabling distributed edge devices to collaboratively train deep neural networks without exchanging raw training data or relying on a central server. Peer-to-Peer Learning (P2PL) and other algorithms…

Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. Training such models, however, is quite inefficient and unstable. In this work, we show how by simply changing the temporal…

Initialising the synaptic weights of artificial neural networks (ANNs) with orthogonal matrices is known to alleviate vanishing and exploding gradient problems. A major objection against such initialisation schemes is that they are deemed…

We introduce QuIC, a training-free quantum graph embedding that maps graphs to sorted output distributions via a fixed parameterized circuit. In the ideal one-repetition setting, we prove that the resulting sorted distribution is…

Multimodal groupwise registration aligns internal structures in a group of medical images. Current approaches to this problem involve developing similarity measures over the joint intensity profile of all images, which may be…

Deep neural networks enable learning directly on the data without the domain knowledge needed to construct a feature set. This approach has been extremely successful in almost all machine learning applications. We propose a new framework…

Deep clustering is a deep neural network-based speech separation algorithm that first trains the mixed component of signals with high-dimensional embeddings, and then uses a clustering algorithm to separate each mixture of sources. In this…